© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29611
    Prev
    Next
    INDEX
    Explanations

    code and numbers

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals with a decimal point (floating-point constants).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zym
    -0.08
    Lin
    -0.07
    HV
    -0.07
     adopts
    -0.07
    236
    -0.07
    -success
    -0.06
     alarmed
    -0.06
    345
    -0.06
    关键
    -0.06
    ylv
    -0.06
    POSITIVE LOGITS
     semantic
    0.06
     філь
    0.06
    (`↵
    0.06
     Россий
    0.06
    >*/↵
    0.06
     Arrange
    0.06
    —for
    0.06
     edt
    0.06
    	dst
    0.06
    (def
    0.06
    Activations Density 0.117%

    No Known Activations